Oj5tVkjbHD@OpenReview

Total: 1

#1 BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces [PDF] [Copy] [Kimi] [REL]

Authors: Matthew Landers, Taylor W. Killian, Hugo Barnes, Thomas Hartvigsen, Afsaneh Doryab

Offline reinforcement learning in high-dimensional, discrete action spaces is challenging due to the exponential scaling of the joint action space with the number of sub-actions and the complexity of modeling sub-action dependencies. Existing methods either exhaustively evaluate the action space, making them computationally infeasible, or factorize Q-values, failing to represent joint sub-action effects. We propose \textbf{Bra}nch \textbf{V}alue \textbf{E}stimation (BraVE), a value-based method that uses tree-structured action traversal to evaluate a linear number of joint actions while preserving dependency structure. BraVE outperforms prior offline RL methods by up to $20\times$ in environments with over four million actions.

Subject: NeurIPS.2025 - Poster